© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 6865
    Prev
    Next
    INDEX
    Explanations

    data synchronization and structure

    np_max-act · gemini-2.0-flash

    This neuron detects the structured section headings and numbering (e.g. “1. Field of the Invention,” “2. Description of the Related Art,” “FIG. …,” etc.) typical of patent documents.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     real
    -0.06
     얻
    -0.06
     của
    -0.06
    ामग
    -0.06
    ż
    -0.06
     添加
    -0.06
     якому
    -0.06
    Sid
    -0.06
     Hyp
    -0.06
     몇
    -0.06
    POSITIVE LOGITS
    lahoma
    0.06
     npc
    0.06
     läng
    0.06
     Lutheran
    0.06
    """,↵
    0.06
    <SpriteRenderer
    0.06
    _prof
    0.06
    "https
    0.06
     ﺍ
    0.06
     недел
    0.06
    Activations Density 0.018%

    No Known Activations